Update app.py

app.py

@@ -6,7 +6,7 @@ client = InferenceClient(model="https://085e2ffe-b85f-4b3d-a764-3ee4f8b84f93.job
 
 def inference(message, history):
     partial_message = ""
-    for token in client.text_generation(message, max_new_tokens=32786, stream=True):
+    for token in client.text_generation(message, max_new_tokens=16393, stream=True):
         partial_message += token
         yield partial_message